Chapter 23 - Cluster-Based Object Tracking by Wireless Camera Networks

Abstract

In this chapter, we present a distributed object tracking system that employs a cluster-based Kalman filter in a network of wireless cameras. Cluster formation is triggered by the detection of objects with specific features. More than one cluster may track a single target, since cameras that see the same object may be outside of each other's communication range. The clustering protocol allows the current state and uncertainty of the target position to be easily handed off among cluster heads as the object is being tracked.